updating base pidgin model with correct tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 46,
+  "<s>": 45
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,47 @@
+{
+  "added_tokens_decoder": {
+    "43": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "45": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "46": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -1 +1,47 @@
-{"g": 0, "/": 1, "e": 2, "0": 3, "'": 4, "x": 5, "\u00e7": 6, "\u00e9": 7, "q": 8, "v": 9, "z": 10, "\u00e8": 11, "5": 12, "d": 13, "6": 14, "f": 15, "c": 16, "@": 17, "t": 18, "i": 20, "o": 21, "2": 22, "a": 23, "b": 24, "h": 25, "8": 26, "p": 27, "4": 28, "r": 29, "w": 30, "7": 31, "k": 32, "j": 33, "1": 34, "y": 35, "s": 36, "m": 37, "u": 38, "9": 39, "l": 40, "3": 41, "n": 42, "|": 19, "[UNK]": 43, "[PAD]": 44}
+{
+  "'": 4,
+  "/": 1,
+  "0": 3,
+  "1": 34,
+  "2": 22,
+  "3": 41,
+  "4": 28,
+  "5": 12,
+  "6": 14,
+  "7": 31,
+  "8": 26,
+  "9": 39,
+  "@": 17,
+  "[PAD]": 44,
+  "[UNK]": 43,
+  "a": 23,
+  "b": 24,
+  "c": 16,
+  "d": 13,
+  "e": 2,
+  "f": 15,
+  "g": 0,
+  "h": 25,
+  "i": 20,
+  "j": 33,
+  "k": 32,
+  "l": 40,
+  "m": 37,
+  "n": 42,
+  "o": 21,
+  "p": 27,
+  "q": 8,
+  "r": 29,
+  "s": 36,
+  "t": 18,
+  "u": 38,
+  "v": 9,
+  "w": 30,
+  "x": 5,
+  "y": 35,
+  "z": 10,
+  "|": 19,
+  "ç": 6,
+  "è": 11,
+  "é": 7
+}